Abstract: 

Predicting unknown outcome values based on their observed features using a model estimated on a training data set is a common statistical problem. Many machine learning and data mining methods have been proposed and shown to be successful when the test data and training data come from the same distribution. However, the best-performing models for a given distribution of training data typically exploit subtle statistical relationships among features, making them potentially more prone to prediction error when applied to test data sets where, for example, the joint distribution of features differs from that in the training data. Therefore, it can be useful to develop predictive algorithms that are robust to shifts in the environment, particularly in application areas where models cannot be retrained as quickly as the environment changes. In this talk, I will describe a view of this problem from correlation versus causality perspective, and describe a number of our recent efforts in this direction.

Bio:

Peng Cui is an Associate Professor with tenure in Tsinghua University. He got his PhD degree from Tsinghua University in 2010. His research interests include network representation learning, causally-regularized machine learning, and social-sensed multimedia computing. He has published more than 100 papers in prestigious conferences and journals in data mining and multimedia. His recent research won the IEEE Multimedia Best Department Paper Award, SIGKDD 2016 Best Paper Finalist, ICDM 2015 Best Student Paper Award, SIGKDD 2014 Best Paper Finalist, IEEE ICME 2014 Best Paper Award, ACM MM12 Grand Challenge Multimodal Award, and MMM13 Best Paper Award. He is the Associate Editors of IEEE TKDE, IEEE TBD, ACM TIST, and ACM TOMM etc.